mlsanityData to 14 Oct 2026

GATSBI: Generative Adversarial Training for Simulation-Based Inference

arXiv 2203.06481 ↗First posted 12 Mar 2022stat.ML cs.LG stat.MEcited by 36

Not on the map. Why?

Abstract (arXiv)

Simulation-based inference (SBI) refers to statistical inference on stochastic models for which we can generate samples, but not compute likelihoods. Like SBI algorithms, generative adversarial networks (GANs) do not require explicit likelihoods. We study the relationship between SBI and GANs, and introduce GATSBI, an adversarial approach to SBI. GATSBI reformulates the variational objective in an adversarial setting to learn implicit posterior distributions. Inference with GATSBI is amortised across observations, works in high-dimensional posterior spaces and supports implicit priors. We evaluate GATSBI on two SBI benchmark problems and on two high-dimensional simulators. On a model for wave propagation on the surface of a shallow water body, we show that GATSBI can return well-calibrated posterior estimates even in high dimensions. On a model of camera optics, it infers a high-dimensional posterior given an implicit prior, and performs better than a state-of-the-art SBI approach. We also show how GATSBI can be extended to perform sequential posterior estimation to focus on individual observations. Overall, GATSBI opens up opportunities for leveraging advances in GANs to perform Bayesian inference on high-dimensional simulation-based models.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 53 of its 80 references that are in the map. First posted on arXiv 12 Mar 2022.

Builds on

53 of 80 references.

References · 53

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  4. 2014Conditional Generative Adversarial Netscited by 2,162
  5. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  7. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  8. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  9. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  10. 2018Which Training Methods for GANs do actually Converge?cited by 679
  11. 2019The frontier of simulation-based inferencecited by 502
  12. 2015Adversarial Autoencoderscited by 364
38 more
  1. 2016Adversarial Feature Learningcited by 350
  2. 2020DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detectioncited by 233
  3. 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 221
  4. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 219
  5. 2016Adversarially Learned Inferencecited by 216
  6. 2017EMNIST: an extension of MNIST to handwritten letterscited by 213
  7. 2016Unrolled Generative Adversarial Networkscited by 208
  8. 2021Projected GANs Converge Fastercited by 208
  9. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 200
  10. 2017Flexible statistical inference for mechanistic models of neural dynamicscited by 163
  11. 2021Benchmarking Simulation-Based Inferencecited by 162
  12. 2020BayesFlow: Learning complex stochastic models with invertible neural networkscited by 144
  13. 2016Learning in Implicit Generative Modelscited by 125
  14. 2018Validating Bayesian Inference Algorithms with Simulation-Based Calibrationcited by 124
  15. 2017Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networkscited by 107
  16. 2020On Contrastive Learning for Likelihood-free Inferencecited by 98
  17. 2015Approximating Likelihood Ratios with Calibrated Discriminative Classifierscited by 90
  18. 2016Likelihood-free inference by ratio estimationcited by 81
  19. 2020Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Samplingcited by 71
  20. 2021Robot Learning from Randomized Simulations: A Reviewcited by 63
  21. 2015Bayesian Optimization for Likelihood-Free Inference of Simulator-Based Statistical Modelscited by 61
  22. 2018Deep Bayesian Inversioncited by 61
  23. 2016Fast ε-free Inference of Simulation Models with Bayesian Conditional Density Estimationcited by 52
  24. 2018Discriminator Rejection Samplingcited by 49
  25. 2017Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Stepcited by 45
  26. 2017Variational Inference using Implicit Distributionscited by 39
  27. 2017Loss-Sensitive Generative Adversarial Networks on Lipschitz Densitiescited by 29
  28. 2017Adversarial Variational Optimization of Non-Differentiable Simulatorscited by 22
  29. 2014GPS-ABC: Gaussian Process Surrogate Approximate Bayesian Computationcited by 17
  30. 2017On Unifying Deep Generative Modelscited by 15
  31. 2017Symmetric Variational Autoencoder and Connections to Adversarial Learningcited by 14
  32. 2014Likelihood-free inference via classificationcited by 13
  33. 2021Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimationcited by 13
  34. 2019Likelihood-free MCMC with Amortized Approximate Ratio Estimatorscited by 10
  35. 2019Likelihood-free approximate Gibbs samplingcited by 8
  36. 2021GATSBI: Generative Agent-centric Spatio-temporal Object Interactioncited by 8
  37. 2020Adversarial Likelihood-Free Inference on Black-Box Generatorcited by 3
  38. 2015Likelihood-free inference in high-dimensional modelscited by 2

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 10; 2024: 10; 2025: 10; 2026: 1.

36 papers.

Sort:

By area:

  1. 2024All-in-one simulation-based inferencecited by 74
  2. 2022Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Modelscited by 50
  3. 2023Learning Robust Statistics for Simulation-based Inference under Model Misspecificationcited by 48
  4. 2023Sampling-Based Accuracy Testing of Posterior Estimators for General Inferencecited by 46
  5. 2022Truncated proposals for scalable and hassle-free simulation-based inferencecited by 41
  6. 2023JANA: Jointly Amortized Neural Approximation of Complex Bayesian Modelscited by 41
  7. 2024Neural Methods for Amortized Inferencecited by 39
  8. 2025Simulation-Based Inference: A Practical Guidecited by 32
  9. 2024Dynamic Conditional Optimal Transport through Simulation-Free Flowscited by 25
  10. 2023Consistency Models for Scalable and Fast Simulation-Based Inferencecited by 22
  11. 2023Efficient Neural Network Approaches for Conditional Optimal Transport with Applications in Bayesian Inferencecited by 20
  12. 2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
24 more
  1. 2022Likelihood-Free Inference with Generative Neural Networks via Scoring Rule Minimizationcited by 15
  2. 2025Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluationcited by 10
  3. 2025Multifidelity Simulation-based Inference for Computationally Expensive Simulatorscited by 9
  4. 2024Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks: An Extended Investigationcited by 8
  5. 2022Contrastive Neural Ratio Estimation for Simulation-based Inferencecited by 7
  6. 2024A Kernel-Based Conditional Two-Sample Test Using Nearest Neighbors (with Applications to Calibration, Regression Curves, and Simulation-Based Inference)cited by 7
  7. 2022Generative Bayesian Inference with GANscited by 6
  8. 2024A Comprehensive Guide to Simulation-based Inference in Computational Biologycited by 6
  9. 2025Multilevel neural simulation-based inferencecited by 5
  10. 2025FNOPE: Simulation-based inference on function spaces with Fourier Neural Operatorscited by 4
  11. 2023Simulation-based Inference with the Generalized Kullback-Leibler Divergencecited by 3
  12. 2023Simulation-based stackingcited by 3
  13. 2024Solving High-dimensional Inverse Problems Using Amortized Likelihood-free Inference with Noisy and Incomplete Datacited by 3
  14. 2023Discriminative calibration: Check Bayesian computation from simulations and flexible classifiercited by 2
  15. 2023Simulation-Based Inference of Surface Accumulation and Basal Melt Rates of an Antarctic Ice Shelf from Isochronal Layerscited by 2
  16. 2024Variational Autoencoders for Efficient Simulation-Based Inferencecited by 2
  17. 2025ConDiSim: Conditional Diffusion Models for Simulation Based Inferencecited by 2
  18. 2024Estimation of System Parameters Including Repeated Cross-Sectional Data through Emulator-Informed Deep Generative Modelcited by 1
  19. 2025A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarioscited by 1
  20. 2026An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learningcited by 1
  21. 2024Kolmogorov-Smirnov GANcited by 0
  22. 2025Learning from Imperfect Data: Robust Inference of Dynamic Systems using Simulation-based Generative Modelcited by 0
  23. 2025Adaptive Symmetrization of the KL Divergencecited by 0
  24. 2025Fast and Robust Simulation-Based Inference With Optimization Monte Carlocited by 0